Bertrande

Cost per point of capability

How much you pay per point of measured capability. This is a division, not an opinion: output price divided by the Artificial Analysis intelligence index. Both numbers are shown so you can redo the calculation yourself.

Where the scores come from. The capability indices are produced by Artificial Analysis, relayed through OpenRouter's catalogue API. They are not our measurement, and we do not run benchmarks ourselves. We record them as a level 4 source and show them next to the price we observed. Prices are what the reseller charges.

ModelIntelligenceCodingOutput priceCost per point
inclusionAI: Ling 3.0 Flash20.650.6$0.063$0.00305825
DeepSeek: DeepSeek V4 Flash 073134.569.1$0.120$0.00347826
Z.ai: GLM 5.3 Flash (batch)41.971.5$0.250$0.00596659
Qwen: Qwen3.5-9B21.828.7$0.150$0.00688073
DeepSeek: DeepSeek V4 Flash 042324.852.0$0.177212$0.00714565
Z.ai: GLM 5.3 Flash41.971.5$0.300$0.00715990
inclusionAI: Ling 3.0 Flash VL25.057.0$0.180$0.0072
inclusionAI: Ling 3.0 Flash Fin23.055.6$0.180$0.00782609
Upstage: Solar Pro 441.652.7$0.360$0.00865385
DeepSeek: DeepSeek V4 Flash 0731 (batch)34.569.1$0.330$0.00956522
Qwen: Qwen3.5-9B (batch)21.828.7$0.250$0.01146789
Google: Gemma 4 26B A4B 26.139.3$0.300$0.01149425
Xiaomi: MiMo-V2.522.356.8$0.280$0.01255605
Mistral: Ministral 3 8B 2512 (batch)5.59.7$0.075$0.01363636
OpenAI: gpt-oss-20b9.020.7$0.130$0.01444444
NVIDIA: Nemotron 3.5 Lightning13.626.8$0.200$0.01470588
DeepSeek: DeepSeek V4.1 Flash39.5n/a$0.600$0.01518987
OpenAI: GPT-5.6 Luna (batch)37.571.4$0.600$0.016
Mistral: Ministral 3 3B 25124.84.8$0.100$0.02083333
OpenAI: GPT-4.1 Nano (batch)9.611.1$0.200$0.02083333
IBM: Granite 4.2 8B11.822.4$0.250$0.02118644
Google: Gemma 4 31B15.443.4$0.340$0.02207792
OpenAI: gpt-oss-20b (batch)9.020.7$0.200$0.02222222
Tencent: Hy3 preview25.858.8$0.600$0.02325581
Nex AGI: Nex-N2-Pro41.759.1$1.00$0.02398082
Mistral: Mistral Small 4 (batch)11.526.6$0.300$0.02608696
NVIDIA: Nemotron 3 Nano 30B A3B8.914.4$0.240$0.02696629
Mistral: Ministral 3 8B 25125.59.7$0.150$0.02727273
OpenAI: GPT-5.4 Nano (batch)21.256.1$0.625$0.02948113
OpenAI: GPT-5.6 Luna37.571.4$1.20$0.032
Xiaomi: MiMo-V2.5-Pro26.460.2$0.870$0.03295455
NVIDIA: Nemotron 3 Super13.637.7$0.450$0.03308824
Mistral: Ministral 3 14B 25126.014.4$0.200$0.03333333
Kwaipilot: KAT-Coder-Pro V233.759.5$1.20$0.03560831
StepFun: Step 3.7 Flash30.939.6$1.15$0.03721683
Qwen: Qwen3 14B6.413.8$0.240$0.0375
Qwen: Qwen3 32B7.215.3$0.280$0.03888889
Google: Gemma 3 12B3.85.8$0.150$0.03947368
MiniMax: MiniMax M329.658.6$1.20$0.04054054
MiniMax: MiniMax M3 (batch)29.658.6$1.20$0.04054054
OpenAI: GPT-4.1 Nano9.611.1$0.400$0.04166667
Google: Gemini 3.8 Flash (batch)41.276.3$1.875$0.04550971
Thinking Machines: Inkling Small26.152.9$1.20$0.04597701
Thinking Machines: Inkling Small (batch)26.152.9$1.20$0.04597701
Meta: Llama 4 Scout6.58.2$0.300$0.04615385
Google: Gemini 3.7 Flash (batch)39.476.1$1.875$0.04758883
Qwen: Qwen3.6 35B A3B18.841.9$0.900$0.04787234
Qwen: Qwen3.6 Plus40.554.5$1.95$0.04814815
OpenAI: gpt-oss-120b12.330.4$0.600$0.04878049
OpenAI: gpt-oss-120b (batch)12.330.4$0.600$0.04878049
Z.ai: GLM 5.3 (batch)44.974.8$2.20$0.04899777
SpaceXAI: Grok Build 0.140.751.5$2.00$0.04914005
Qwen: Qwen3.7 Plus25.855.9$1.28$0.04961240
Z.ai: GLM 4.734.545.3$1.75$0.05072464
MiniMax: MiniMax M2.723.252.6$1.20$0.05172414
Mistral: Mistral Small 411.526.6$0.600$0.05217391
Z.ai: GLM 5.234.068.8$1.80$0.05294118
Qwen: Qwen3.5-35B-A3B24.337.0$1.30$0.05349794
OpenAI: GPT-4.1 Mini (batch)14.820.2$0.800$0.05405405
DeepSeek: DeepSeek V4 Pro 081336.368.8$1.98$0.05454545

60 models ranked, out of those for which we hold both a published price and a capability score. A model missing from this table is missing a figure, not judged.